© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 98076
    Prev
    Next
    INDEX
    Explanations

    historic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     initComponents
    -0.78
    HasForeignKey
    -0.71
     bezeichneter
    -0.70
    httphttps
    -0.68
     ویکی‌پدیا
    -0.67
     GenerationType
    -0.65
     defaultstate
    -0.65
    Hochspringen
    -0.64
     typelib
    -0.64
    MemoryWarning
    -0.64
    POSITIVE LOGITS
    -
    0.60
     centre
    0.59
     center
    0.57
     and
    0.53
    hold
    0.49
     &
    0.49
     region
    0.47
    ,
    0.47
     monument
    0.46
     G
    0.44
    Activations Density 0.016%

    No Known Activations